{"id":"W4313414396","doi":"10.3390/f14010053","title":"An SSD-MobileNet Acceleration Strategy for FPGAs Based on Network Compression and Subgraph Fusion","year":2022,"lang":"en","type":"article","venue":"Forests","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Field-programmable gate array; Pruning; Hardware acceleration; Artificial neural network; Scheduling (production processes); Acceleration; Algorithm; Quantization (signal processing); Artificial intelligence; Real-time computing; Computer engineering; Machine learning; Embedded system; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001730254,0.0001226916,0.0001048909,0.00006293176,0.0007464247,0.00008940613,0.0004426522,0.00003259086,0.00001428009],"category_scores_gemma":[0.000004490223,0.0001187172,0.00003287171,0.0003537031,0.00002305377,0.0002761101,0.0001411306,0.0001278229,0.000001615265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003029067,"about_ca_system_score_gemma":0.00003399889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000579108,"about_ca_topic_score_gemma":0.0000803109,"domain_scores_codex":[0.9988485,0.0000906717,0.0001592075,0.0004377012,0.0002136114,0.0002503328],"domain_scores_gemma":[0.9991091,0.000162355,0.00009863932,0.0004983293,0.00003796814,0.00009354216],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004960717,0.00008400923,0.001750604,0.000005346227,0.000001462744,0.000001365105,0.00002966939,0.9280667,0.0005886627,0.02525743,0.003445964,0.04071917],"study_design_scores_gemma":[0.0004334981,0.00063386,0.03343499,0.000009290308,0.000003009077,0.00000300544,0.000004700437,0.9403607,0.0003188306,0.01898321,0.005669927,0.0001450043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1905395,0.00008664554,0.8073845,0.0004204144,0.0002248221,0.0009734069,0.00001829064,0.0002095739,0.0001428207],"genre_scores_gemma":[0.9811935,0.000006619274,0.0174676,0.0004457127,0.0001335277,0.0005844558,0.0001229055,0.00001434912,0.00003129047],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.790654,"threshold_uncertainty_score":0.574097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02883801866558267,"score_gpt":0.3002388521970409,"score_spread":0.2714008335314582,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}